faiss cli lib

3 files changed, 99 insertions, 0 deletions

diff --git a/megapixels/cli_faiss.py b/megapixels/cli_faiss.py
new file mode 100644
index 00000000..9953d9b7
--- /dev/null
+++ b/megapixels/cli_faiss.py
@@ -0,0 +1,36 @@
+# --------------------------------------------------------
+# add/edit commands in commands/faiss directory
+# --------------------------------------------------------
+
+import click
+
+from app.settings import app_cfg as cfg
+from app.utils import logger_utils
+from app.models.click_factory import ClickSimple
+
+# click cli factory
+cc = ClickSimple.create(cfg.DIR_COMMANDS_FAISS)
+
+# --------------------------------------------------------
+# CLI
+# --------------------------------------------------------
+@click.group(cls=cc, chain=False)
+@click.option('-v', '--verbose', 'verbosity', count=True, default=4, 
+  show_default=True,
+  help='Verbosity: -v DEBUG, -vv INFO, -vvv WARN, -vvvv ERROR, -vvvvv CRITICAL')
+@click.pass_context
+def cli(ctx, **kwargs):
+  """\033[1m\033[94mMegaPixels: FAISS Data Scripts\033[0m                                                
+  """
+  ctx.opts = {}
+  # init logger
+  logger_utils.Logger.create(verbosity=kwargs['verbosity'])
+
+
+
+# --------------------------------------------------------
+# Entrypoint
+# --------------------------------------------------------
+if __name__ == '__main__':
+    cli()
+
diff --git a/megapixels/commands/faiss/build.py b/megapixels/commands/faiss/build.py
new file mode 100644
index 00000000..e95619af
--- /dev/null
+++ b/megapixels/commands/faiss/build.py
@@ -0,0 +1,46 @@
+"""
+Index all of the FAISS datasets
+"""
+
+import os
+import click
+
+from app.utils.file_utils import load_recipe, load_csv
+from app.settings import app_cfg as cfg
+
+@click.command()
+@click.pass_context
+def cli(ctx):
+  """train the FAISS index"""
+  
+  recipe = {
+    "dim": 128,
+    "factory_type": "Flat"
+  }
+
+  datasets = []
+  for fn in glob.iglob(os.path.join(cfg.DIR_FAISS_DATASETS, "*")):
+    name = os.path.basename(fn)
+    recipe_fn = os.path.join(cfg.DIR_FAISS_RECIPES, name + ".json")
+    if os.path.exists(recipe_fn):
+      train(name, load_recipe(recipe_fn))
+    else:
+      train(name, recipe)
+
+def train(name, recipe):
+  vec_fn = os.path.join(cfg.DIR_FAISS_DATASETS, name, "vecs.csv")
+  index_fn = os.path.join(cfg.DIR_FAISS_INDEXES, name + ".index")
+
+  index = faiss.index_factory(recipe.dimension, recipe.factory)
+
+  keys, rows = file_utils.load_csv_safe(vec_fn)
+  feats = np.array([ float(x[1].split(",")) for x in rows]).astype('float32')
+  n, d = feats.shape
+
+  train_start = time.time()
+  index.train(feats)
+  train_end = time.time()
+  train_time = train_end - train_start
+  print("{} train time: {:.1f}s".format(name, train_time))
+
+  faiss.write_index(index, index_fn)
diff --git a/megapixels/commands/faiss/sync.py b/megapixels/commands/faiss/sync.py
new file mode 100644
index 00000000..ae13b948
--- /dev/null
+++ b/megapixels/commands/faiss/sync.py
@@ -0,0 +1,17 @@
+"""
+Sync the FAISS metadata
+"""
+
+import subprocess
+import click
+
+from app.settings import app_cfg as cfg
+
+@click.command()
+@click.pass_context
+def cli(ctx):
+  sts = call([
+    "s3cmd", "sync",
+    "s3://megapixels/v1/metadata/",
+    cfg.DIR_FAISS_METADATA,
+  ])